NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1GRHB7PCJSEYYNMFW497DN
Run Details
Model:
GPT-5.4
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.5s
Cost:
$0.004335
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
97.92%
Dialogue to Total Word Ratio
(details)
94.1998%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly and Bill crouched behind the municipal hedge, the one trimmed into a rabbit with a tragic underbite, and studied the battlefield of balloons. Across the lawn, a children’s party raged with the lawless energy of a tiny dictatorship: paper crowns askew, cake smeared like war paint, a clown folding balloons with the grim focus of a bomb technician. In the center, beneath a gazebo strung with bunting, sat the mountain of presents, gleaming in cartoon paper and guarded only by a distracted aunt and a spaniel in a tutu. Bill adjusted his cap and squinted through opera glasses he’d stolen from someone much richer and far less vigilant. “In, grab, out,” he whispered. “Brilliant,” Molly muttered. “And if the clown sees us?” “We become entertainment.” Molly checked the contents of her satchel: rope, torch, fake invitations, and a slice of sausage roll she considered strategic. Bill, meanwhile, had brought marbles, a smoke pellet, and entirely too much confidence. Together they had the posture of professionals and the planning habits of escaped geese. A gust carried the smell of icing and impending disaster. Molly smiled the way burglars do when they’ve mistaken a terrible idea for a clever one. Then the spaniel looked up, tutu trembling, and began to growl.
created_at
"2026-03-06T12:08:07.279Z"
3/6/2026, 12:08:07 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
379
moderation_latency
(null)
generation_time
9405
tokens_prompt
77
tokens_completion
336
native_tokens_prompt
66
native_tokens_completion
278
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.004335
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_085cc26cac7bdf750169aac3a756048194b530f0519f985a39"
is_byok
false
latency
146
model_permaslug
"openai/gpt-5.4-20260305"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1772798887-BC9GBdpwDZ4XXvWTq9Qq"
upstream_id
"resp_085cc26cac7bdf750169aac3a756048194b530f0519f985a39"
total_cost
0.004335
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
210
97.92%
Dialogue to Total Word Ratio
Ratio: 6.19%, Deviation: 3.81%
neededClean
false
wordsTotal
210
wordsDialogue
13
94.1998%